Receita Federal: NFS-e

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explains the two authentication modes (permanent vs session) and the flow of getting a token. It does not mention potential side effects like token invalidation or rate limits, but the idempotent hint is consistent and no contradiction exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately concise but somewhat run-on. It contains all necessary information in two sentences, but the structure could be tidier (e.g., separating the permanent and session options more distinctly).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple schema (one optional param) and annotations, the description covers how to use the tool and what to expect (link generation, token authentication). It does not explicitly mention return values or error cases, but these are not critical for an auth tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter 'token' is clearly explained: it is optional, used for session-only authentication when passed, and omitted to obtain the login link. This fully clarifies the parameter's role.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: authenticating with MCP.AI for IDE agents. It explicitly mentions 'log in' and 'access token', making the resource and action unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides detailed step-by-step instructions: log in via browser, copy token, then either add to server config for permanent connection or pass token as parameter for session login. Also explains the no-args option to retrieve the login link.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the annotations by explaining conditional behavior: it returns authenticated:true with empty pending[] when all providers are connected, and connect_url plus per-install URLs when credentials are missing. This adds meaningful behavioral context that annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary purpose, and every sentence adds useful information. There is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple status-check tool with no parameters and no output schema, the description covers the main return scenarios and key fields. It could be slightly more explicit about what pending[] represents, but it is largely complete for the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the schema coverage is 100%, so there are no parameter semantics to explain. The baseline of 4 for a no-parameter tool is appropriate since the description cannot add parameter-level detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns connection status and URLs, which is a specific verb+resource combination. It distinguishes itself from siblings like authenticate by focusing on status reporting rather than performing authentication.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is used to check connection status and retrieve URLs when credentials are missing, but it does not explicitly state when to use it versus alternatives like authenticate. No exclusions or alternative tool references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false; description goes beyond by explaining invoke's one-off behavior without bloating toolkit, the fact that writes require workspace owner/admin, and the credential/checkout link flow. It doesn't specify what happens on partial failures or exact permission errors, but adds significant context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is comprehensive but dense, covering the entire marketplace including prompt library in one block. It front-loads the core flow but lacks segmentation or breaking down per action. Some redundancy with annotations (e.g., 'official mcp.ai marketplace' repeated). It earns its place but could be structured for better scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's high complexity (14 actions, 23 params, no output schema), the description conveys the full domain and the distinguishing logic between actions, including the key invoke non-install behavior and the prompt library. It doesn't explain return structures or error handling, but with no output schema and the tool being a multi-purpose dispatcher, the description covers most critical contextual gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so description must compensate. Description explains high-level purpose of action values and parameters like mcp_id, tool_id, prompt_slug, but many parameters (limit, immediate, conversation, report_context, request_details, etc.) are not elaborated, and there's no per-parameter detail beyond what the defaults suggest. With 23 params and no schema descriptions, the description is insufficient for understanding all parameter combinations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description precisely states the tool's role: the official mcp.ai marketplace, a catalog and execution platform for MCPs. It clearly differentiates from siblings by describing the core flow (search → describe → invoke) and explicitly lists the other tools' purposes (list_tools, subscribe/cancel, report_bug, request_mcp) and the separate prompt library functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use vs alternatives: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT', 'list_tools lists what is callable right now'. Also explains the key behavior when invoke runs without installation and how to handle credential/checkout cases with retry instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses payment via prepaid credit, hosting by the platform without credentials, and LGPD data controller responsibilities. This adds meaningful operational and legal context beyond what annotations already provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with multiple clauses, mixing purpose, payment, and legal compliance. While front-loaded with the core purpose, the later sentences are verbose and could be condensed or moved to separate metadata. It is not overly long but not tightly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter query tool with good annotations, the description provides operational and legal context, but it omits parameter meaning and the expected return behavior. With no output schema, agents are left to infer how the data is returned (e.g., data payload, status, error codes). This is a moderate gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description fails to explain the single required parameter 'chave'. It does not state what the key represents (e.g., NFS-e access key, registration number), leaving the agent without any semantic guidance. The description must compensate but does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's purpose: 'NFS-e, consulta em fonte oficial' (NFS-e query in official source). It specifies the resource (NFS-e) and the source (Receita Federal), and the verb 'consulta' matches the tool name. This distinguishes it from the unrelated sibling tools like authenticate or marketplace.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (querying official Brazilian sources) and mentions operational prerequisites (no platform credentials, prepaid credit). However, it does not provide explicit when-to-use vs. alternatives or any exclusions. Since siblings are unrelated, this is adequate but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is known. The description adds the detail about including conversation for reproduction, which gives context on what the tool expects but does not disclose side effects or response behavior. The description does not contradict annotations, and the additional context is useful but limited.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences long and conveys the purpose, scope, and a key usage hint. Every word earns its place; there is no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (3 parameters, no output schema), the description covers the core purpose and one parameter. However, it omits any explanation of the 'message' (the actual report content) and 'context' parameters, which may leave the agent unsure of what to provide. The conversation hint is useful but incomplete for a fully self-sufficient description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description only explicitly explains the 'conversation' parameter ('Include the conversation array with recent messages for reproduction'). The required 'message' parameter and the 'context' parameter are not described, leaving them ambiguous. Since the description fails to compensate for the lack of schema descriptions on two out of three parameters, it adds only partial value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Report a bug, missing feature, or send feedback.' It names the specific resources (bug, feature, feedback) and distinguishes from sibling tools like authenticate or show_version, which have entirely different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context on when to use the tool (for reporting issues or feedback) and provides a usage instruction: 'Include the conversation array with recent messages for reproduction.' It does not explicitly mention alternatives or exclusions, but siblings are unrelated, making the intended usage obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the word 'current' which implies a real-time snapshot, but that is minimal additional behavioral context. No contradictions exist, and the annotation coverage reduces the burden on the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that directly states the tool's function. Every word earns its place, and there is no fluff or redundancy, making it exemplary in terms of brevity and clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only tool with good annotations and no output schema, the description is fully sufficient. It communicates exactly what the tool does without requiring additional context. The sibling tools do not create confusion, and the simple nature of the tool means no further details are needed for an agent to select and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the schema is trivially complete. With no parameters to explain, the description doesn't need to add parameter-specific meaning. The baseline score of 4 for zero-parameter tools is appropriate, as there is nothing to clarify beyond the tool's intent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Show the current MCP platform and adapter versions.' It uses a specific verb ('show') and a specific resource ('MCP platform and adapter versions'), making it unambiguous. None of the sibling tools (authenticate, connect, marketplace, etc.) appear to overlap with this functionality, so it is well distinguished.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly conveys when to use the tool: whenever version information is needed. There are no obvious alternative tools for this purpose within the sibling list, so no explicit exclusions are necessary. The context is clear, though it doesn't explicitly state 'use when you need version info'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by specifying what the state includes (installed MCPs, connection status, accounts, catalog tools count), which goes beyond the annotation details. It does not introduce contradictions and provides useful context about the tool's read-only nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys the full purpose. Every clause adds relevant information (installed MCPs, connection status, accounts, catalog tools count) without any wasted words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only info tool with no parameters and no output schema, the description adequately lists what the tool returns. It could mention that it returns a summary or a breakdown, but the current description is sufficient for an agent to understand the tool's functionality. The lack of output schema is not a major gap because the description enumerates the returned aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema fully covers parameter semantics. The description does not need to explain parameters. According to the rubric, a baseline of 4 is appropriate for a tool with no parameters, and the description does not detract from this.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the current toolkit state with specific details (installed MCPs, connection status, accounts, catalog tool counts). This distinguishes it from siblings like show_version (which is about version) and authenticate/connect (which are actions). The verb 'Returns' plus the resource 'current toolkit state' makes the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for checking overall toolkit state, but it does not explicitly state when to use it versus alternatives. There is no mention of when not to use it or other tools that might be more appropriate. However, given it is a standalone info tool with no direct sibling overlap, the context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.